Find US court cases, opinions and dockets naming a business entity. Returns normalized records with case name, court, date, citation, docket number and nature of suit, plus a total count. Source: CourtListener, public-domain.

Look up the US patent portfolio of an organization (by assignee) or an inventor (by name). Returns granted patents with id, title, grant date, type and assignees, plus a total count. Source: USPTO PatentsView, public-domain.

Composite legal due-diligence profile of a business entity: litigation, patents and federal regulatory records in one call, plus a deterministic legal-risk signal (score 0-100, band, per-dimension flags and reasons).

Find US federal regulatory and enforcement documents mentioning an entity in the Federal Register. Returns rules, proposed rules and notices with title, type, agency, date, abstract and link. Source: Federal Register, public-domain.

Look up one US federal bill by id: title, sponsor, cosponsors, committees, policy area, full action history and computed lifecycle stages (introduced to enacted). Source: Congress.gov + GovInfo, public-domain.

Find US proposed rules and rulemaking dockets by docket id, keyword or agency: documents, comment period, public-comment count and Federal Register links. Source: Regulations.gov + Federal Register, public-domain.

Search US federal bills by keyword (optionally within one Congress) and get a ranked list of matching bills with id, title and latest action. Source: Congress.gov, public-domain.

Stateless event diff for a US federal bill: which lifecycle stages it reached over a date window (introduced, committee, passed, enacted), each with date and source action. Source: Congress.gov, public-domain.

On-chain DeFi liquidation telemetry for Base lending protocols: recent LiquidationCall events decoded by us from public Base event logs — count, total debt repaid and collateral seized (USD), estimated liquidation bonus, per-protocol and per-asset breakdown, and the recent events (user, liquidator, collateral, debt).

DeFi lending protocol-health + solvency intelligence for a protocol or asset on Base: per-market utilization, available liquidity, TVL, total borrowed, debt ceiling and a deterministic 0-100 health score plus verdict (healthy / tight-liquidity / elevated), protocol aggregates, and a rate/TVL trend — computed by us over DefiLlama data.

Cross-protocol DeFi money-market supply/borrow rates for an asset on Base: per-market supply APY, borrow APY, reward APY, utilization, LTV and available liquidity across Aave/Compound/Morpho/Euler/Fluid/Moonwell, plus a risk-aware best-safe-yield ranking (safety-flagged, not naked max APY), fused by us from DefiLlama pools+lendBorrow.

License-compliance verdict for one package and its whole transitive dependency tree. Resolves the deps.dev graph plus the declared SPDX license of every node, finds copyleft contamination points, and returns a target-and-distribution-aware verdict of safe, attribution-required, copyleft-risk or incompatible. Automated indicators, not legal advice.

Pure-compute license-compatibility verdict, no network. Give a list of SPDX ids or one SPDX expression with AND, OR and WITH plus a target license and a distribution model, and get the matrix verdict of safe, attribution-required, copyleft-risk or incompatible with the obligation and reasons. Automated indicators, not legal advice.

License-compliance verdict for a whole dependency list or parsed manifest in one call. Accepts name-at-version strings, a parsed package.json, a requirements.txt list or go.mod imports, resolves each declared SPDX license, and returns a per-dependency plus aggregate verdict with the worst copyleft contamination point. Automated indicators, not legal advice.

Extract every link from a public page for crawling agents: de-duplicated absolute URLs with anchor text, internal/external counts, declared feeds and a sitemap hint.

Federal lobbying filings from the Senate LDA disclosure system covering both chambers. Give a client name, registrant firm name, lobbyist name or issue code and get normalized filings with the registrant, client, reported income or expenses, issue areas, government entities lobbied and the lobbyists, each cited to its filing document. Optional filing year and period filters.

Lobbying-spend profile for a company or organization by name. Fuses the entity's Senate LDA filings into total reported spend by year with a trend, the top issue areas and the registrant firms it hired, plus recent cited filings. Optionally adds a bounded summary of the LD-203 political contributions reported by its top registrant firms.

One indicator compared across several countries: the latest value for each plus computed signals — rank, highest and lowest, spread and mean. Each value is cited to its source.

A curated headline basket of key macroeconomic and development indicators for one country: GDP, GDP per capita, growth, inflation, unemployment, population, government debt, current account, life expectancy and CO2 per capita. Latest value plus short history, each value cited to its source.

IMF World Economic Outlook forecasts for a country: real GDP growth, inflation, nominal GDP, GDP per capita, government debt, current account and unemployment, including projected future years. Values are cited to the IMF WEO.

One macroeconomic or development indicator for one or more countries as a cited time-series. Fuses free authoritative sources (World Bank, IMF) and tags every value with its source, source code, year and country ISO3. Accepts a canonical indicator key or a raw World Bank code.

Rich cross-source market report: Chainlink + DEX pools, TVL-weighted VWAP, total pool TVL, recent change & volatility — all computed by us from on-chain state.

Deduplicate a list of names or addresses into clusters of likely duplicates. Blocks by similarity key then confirms pairwise inside each block, returning clusters with a canonical representative plus a summary of input, cluster and duplicate counts. Similarity indicators, not authoritative identity resolution.

Compute a deterministic similarity key for a name or address: the cheap first step of client-side blocking and deduplication. Records that share a key are duplicate candidates to confirm. Returns the key, the normalized form and the tokens. Indicators, not authoritative identity resolution.

Fuzzy-match two names or addresses and return a 0-100 similarity score with a match decision. Normalizes legal forms, business stop-words, person titles and address abbreviations BEFORE the fuzzy compare, then fuses token, prefix, phonetic and edit similarity. Returns the score, the per-component scores, the normalized forms and is_match. Similarity indicators, not authoritative identity resolution.

Standardize a company name, person name or address to a canonical form. Canonicalises legal forms, drops business stop-words, strips person titles and suffixes and folds address abbreviations. Returns the canonical form, the tokens and the rules that were applied. Indicators, not authoritative identity resolution.

Static security scan of a single text or prompt blob: hidden unicode, prompt injection, data-exfiltration directives, dangerous-capability and tool-shadowing language, and obfuscation. Returns a 0-100 risk score, category and findings. Security indicators, not a guarantee.

Static security scan of an MCP manifest or tool list. Detects tool poisoning, hidden unicode instructions, prompt injection, data-exfiltration directives, dangerous capabilities, tool shadowing and post-approval rug-pull drift. Returns a 0-100 risk score, category, per-tool findings and content hashes. Security indicators, not a guarantee.

Batch safety preflight for many database migrations at once: a list of objects each with a name and migration SQL. Returns a per-file pass, caution or block verdict plus a rollup with the worst verdict and counts. Migration-safety indicators, not a guarantee.

Safety preflight for a database schema migration BEFORE you apply it. Send the migration SQL for Postgres or MySQL and get a pass, caution or block verdict with per-finding operation, severity, plain-language reason and a zero-downtime alternative. Migration-safety indicators, not a guarantee.

ASIC-miner break-even and profitability: daily and monthly BTC and USD revenue, power cost, net profit, margin, the break-even electricity price and the break-even BTC price, and optional hardware payback days, for a named miner model or raw hashrate and wattage at a given electricity price. Informational, not advice.

Bitcoin hash-ribbon miner-capitulation signal: the 30-day versus 60-day moving average of network hashrate, whether miners are in capitulation, whether a recovery cross has occurred, and the 30-day hashrate trend. Informational, not advice.

Bitcoin mining hashprice: expected mining reward per petahash and per terahash per second per day, in BTC and USD, fused with the network hashrate, current difficulty, the next difficulty-retarget forecast and the block-subsidy and average-fee split. Informational, not advice.

Compare two to five models side by side. Give a comma separated list of names or aliases and get each model normalized on price, context, capabilities, knowledge cutoff and coding benchmark, plus flags for the cheapest, the best benchmark and the largest context. Fused from open keyless catalogs with a citation on every model.

Look up one normalized model record by name or short alias such as sonnet or 4o. Returns per-million input and output prices, context and output limits, capability tags, modalities, knowledge cutoff, release date, provider and coding benchmark, each fused from open keyless catalogs LiteLLM, models dev and Aider with a source citation. Unknown names return found false, never an error.

Pick the cheapest LLM that passes your task and constraints. Give a task class and optional constraints such as minimum context, required tool-use, vision or reasoning, maximum input and output price per million tokens, a minimum coding benchmark and a provider filter, and get a ranked cheapest-first list of models that pass, plus a recommended pick and a deterministic rationale. Fused from open keyless catalogs LiteLLM, models dev and Aider with a citation on every model.

Registry and routing metadata for an autonomous system: the AS name, the Regional Internet Registry that allocated it, the country, the allocation date and status, a datacenter/hosting classification and the announced-prefix count.

Full routing-security report for an IPv4 address or prefix: the origin AS, the RIR allocation of the block (who, when, country, status), the RPKI ROA status against that origin, and more-specific and less-specific ROA coverage.

RPKI Route-Origin Validation for an IPv4 prefix and origin AS, computed per RFC 6811 from the bulk Validated ROA Payload set. Returns the ROA status, the covering ROA count and the matching ROAs with their origin, max length and trust anchor.

Situation brief on a topic (RAG over fresh news): searches recent news, reads the top articles and synthesizes a short cited summary of what is currently happening plus key points. Cites only the retrieved articles (anti-hallucination).

Normalized multi-period Form 990 financials for a US nonprofit by EIN: revenue, expenses, contributions, program revenue, assets, liabilities, net assets and officer compensation per tax year, plus computed ratios (program support, overhead, officer-compensation share, net margin) and gap flags, each number cited to its filing.

Composite due-diligence profile of a US 501(c) nonprofit by EIN or name: identity (name, EIN, decoded NTEE, subsection, foundation type, ruling date), current IRS status fusion (Pub 78 deductibility, auto-revocation, exempt status), latest Form 990 financials, multi-year trend, cited filings, and a deterministic health and risk indicator set.

Resolve a US nonprofit name to ranked candidate organizations, each with EIN, name, city, state, decoded NTEE, subsection and a match score. The cheap first step for EIN-to-name disambiguation, optionally narrowed by state, NTEE category or 501(c) subsection.

Crisp authoritative IRS tax-exempt status for a US nonprofit by EIN: whether it is currently tax-exempt, listed in Publication 78 as able to receive deductible contributions with the eligibility code, whether its status was automatically revoked with the revocation and reinstatement dates, and its 501(c) subsection.

Notarize a public URL: we fetch it ourselves and return a signed snapshot (final URL, HTTP status, content-type, sha256 of the body, server timestamp, upstream host) with TWO cryptographic attestations — a plain EIP-712 signature and an EAS off-chain (Version2) attestation. Proves what this endpoint observed at fetch time (integrity + timestamp + non-repudiation). mode=hash (default) returns metadata + hash only; mode=full also returns the body.

Look up a packaged product by GTIN/barcode via Open Food Facts (global). Returns the normalized nutrition profile plus allergens, diet flags, Nutri-Score and NOVA.

Full normalized nutrition profile for a USDA FoodData Central food by fdc_id: calories, macros and micronutrients per 100g and per serving.

Search foods by name in USDA FoodData Central (public domain). Returns ranked matches with fdc_id, description, brand, GTIN and key macros per 100g.

Workplace-safety risk verdict for a US employer from public OSHA enforcement records. Give an establishment name and optional state and get a 0-100 safety risk score, a low, medium, high or critical rating, per-dimension flags, reasons and a cited list of the inspections behind the score. Deterministic, no LLM. Risk indicators, not legal or compliance advice.

Search US employers in the public OSHA enforcement records by establishment name and get ranked candidates, each with its state, SIC and NAICS codes, last inspection date, inspection count, summed violation count and the most serious inspection trigger. Cheap first step before osha/company.